Research map / Point clouds / Registration and matching
PointCLM: A Contrastive Learning-Based Framework for Multi-Instance Point Cloud Registration
Mingzhi Yuan, Zhihao Li, Qiuye Jin, Xinrong Chen, Manning Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add deep contrastive representation (ablation) | PointCLM · Scan2CAD | MF (%): 70.36 -> 74.18 | Improved |
| add deep contrastive representation (ablation) | PointCLM · Scan2CAD | Time (s): 0.17 -> 0.10 | Improved |
| add pruning (ablation) | PointCLM · Scan2CAD | MF (%): 42.93 -> 74.18 | Improved |
| use hardest negative pairs instead of random (ablation) | PointCLM · Scan2CAD | MF (%): 71.87 -> 74.18 | Improved |
| increase RANSAC iterations from 5 to 50 (ablation) | PointCLM · Scan2CAD | MF (%): 72.26 -> 74.18 | Improved |
| increase RANSAC iterations from 50 to 500 (ablation) | PointCLM · Scan2CAD | MF (%): 74.18 -> 74.73 | No clear effect |
| raise tau_S from 0.85 to 0.90 (ablation) | PointCLM · Scan2CAD | MR (%): 78.10 -> 74.06 | Hurt |
| lower tau_S from 0.85 to 0.75 (ablation) | PointCLM · Scan2CAD | MF (%): 74.18 -> 73.71 | No clear effect |
| lower tau_N from 20 to 10 (ablation) | PointCLM · Scan2CAD | MP (%): 70.64 -> 61.44 | Hurt |
| lower tau_N from 20 to 10 (ablation) | PointCLM · Scan2CAD | MR (%): 78.10 -> 80.60 | Improved |
| random negatives vs no deep representation (ablation) | PointCLM · Scan2CAD | MF (%): 70.36 -> 71.87 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports PointCLM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.91)
- Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes (CVPR 2024 · similarity 0.89)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · similarity 0.89)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.88)
- Inlier Confidence Calibration for Point Cloud Registration (CVPR 2024 · similarity 0.88)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
